Electronic signature generation and anti-counterfeiting system based on multi-source information fusion

Abstract

The invention discloses an electronic signature generation and anti-counterfeiting system based on multi-source information fusion, and the system comprises a multi-source information collection module which is used for synchronously obtaining the fingerprint / iris characteristics of a user, the hardware fingerprint of terminal equipment, and the timestamp and geographical location information during operation; the information fusion processing module is used for encrypting and compressing the multi-source information and generating a unique feature vector by adopting a weighted feature fusion algorithm and a block chain encryption anchoring technology; the electronic signature generation module is used for generating a visual signature graph containing a dynamic digital watermark and a multi-layer nested timestamp based on the feature vector, and writing a feature vector hash value into a block chain for evidence storage; and the anti-counterfeiting verification module performs authenticity verification on the signature through a dynamic decryption protocol distributed by a quantum key, and supports reverse feature matching verification based on block chain traceability. According to the invention, the limitation of a traditional single encryption mode is broken through through the cross binding of the multi-mode biological characteristics and the hardware fingerprints in combination with the quantum key and block chain fragmentation technology.

Description

Technical Field

[0001] The present invention belongs to the technical field of electronic signatures, and in particular relates to an electronic signature generation and anti-counterfeiting system based on multi-source information fusion. Background Art

[0002] With the rapid development of information technology, electronic signatures are increasingly used in e-government, e-commerce, e-finance and other fields. Traditional electronic signature technology mainly relies on a single source of information, such as digital certificates or simple biometrics, which have certain limitations in terms of security, reliability and adaptability. For example, single biometrics may be affected by forgery or replay attacks, while simple digital certificates may lose security due to private key leakage.

[0003] In order to meet these challenges, multi-source information fusion technology has gradually become a research hotspot in the field of electronic signatures. Multi-source information fusion can combine different types of information sources, such as biometrics, device fingerprints, and dynamic environmental information, and improve the security and reliability of electronic signatures by comprehensively analyzing and processing this information. At the same time, the rise of blockchain technology has provided new ideas for the anti-counterfeiting verification of electronic signatures. Its distributed storage, non-tamperable and traceable characteristics can effectively enhance the credibility and anti-tampering capabilities of electronic signatures. Summary of the invention

[0004] In view of this, the present invention proposes an electronic signature generation and anti-counterfeiting system based on multi-source information fusion, which breaks through the limitations of the traditional single encryption mode by cross-binding multimodal biometrics and hardware fingerprints, combining quantum keys and blockchain sharding technology.

[0005] In order to achieve the above object, the present invention provides the following technical solutions: The present invention provides an electronic signature generation and anti-counterfeiting system based on multi-source information fusion, comprising: The multi-source information acquisition module includes a user biometric feature recognition unit, a device fingerprint extraction unit, and a dynamic environment perception unit, which are used to synchronously obtain user fingerprint / iris features, terminal device hardware fingerprints, and timestamps and geographic location information during operation; The information fusion processing module uses a weighted feature fusion algorithm and blockchain encryption anchoring technology to encrypt and compress multi-source information and generate a unique feature vector; The electronic signature generation module generates a visual signature graphic containing a dynamic digital watermark and a multi-layer nested timestamp based on the feature vector, and writes the feature vector hash value into the blockchain for evidence storage; The anti-counterfeiting verification module verifies the authenticity of the signature through the dynamic decryption protocol of quantum key distribution, and supports reverse feature matching verification based on blockchain traceability.

[0006] Preferably, the multi-source information acquisition module includes: User biometric identification unit: used to collect fingerprint line features, iris texture phase coding and voiceprint dynamic spectrum through multi-threaded parallelization through fingerprint sensor, iris scanner and microphone array; Device fingerprint extraction unit: used to extract CPU microcode features, baseband chip serial number and GPU rendering fingerprint by parsing the hardware registers of the terminal device, and generate a composite device identification code; Dynamic environment perception unit: used to capture the three-dimensional geographic coordinates, UTC timestamp and device motion trajectory characteristics during operation in real time through the built-in GPS / Beidou dual-mode positioning chip, NTP network timing module and acceleration sensor; The multi-source information collection module runs in isolation through a secure sandbox, and the collected data is transmitted to the information fusion processing module after being signed by HMAC-SHA3.

[0007] Preferably, the information fusion processing module includes: A data preprocessing unit is used to normalize the biometric data, wherein the fingerprint image is denoised using Gabor filtering, and the iris feature is compressed to a 256-dimensional vector through Daubechies wavelet transform; The weighted feature fusion unit dynamically assigns weight coefficients to biological features, equipment features, and environmental features based on the preset environmental risk assessment model, and calculates the fusion features using the weighted Euclidean distance formula: ,in, , , They are the dynamic real-time feature values ​​of biometric features, device features, and environmental features. , , They are the dynamic baseline values ​​of biometrics, device features, and environmental features. , , They are the maximum tolerances of each dimension of biometrics, device features, and environmental features. , , They are the weight coefficients corresponding to the dynamics of biometric features, device features, and environmental features; The blockchain encryption anchor unit is used to encrypt the fused feature value through the national secret SM4 algorithm. After generating a 256-bit feature vector, its hash value is written into the Merkle tree of the Hyperledger Fabric alliance chain, and a timestamp and participating node digital certificate are generated for each signed transaction.

[0008] Preferably, the electronic signature generation module includes: The watermark embedding unit is used to generate a pseudo-random sequence from the feature vector through chaotic mapping, and to embed the digital watermark in the intermediate frequency component of the signature image using discrete cosine transform. The embedding strength is adaptively adjusted based on the network delay. The timestamp generation unit is used to call the National Time Service Center API to obtain the Beidou atomic clock time, trigger the Ethereum smart contract to generate an on-chain time certificate containing the hash of the previous block, perform SHA-256 hash operation on the signature file content, encrypt it after splicing it with the user's biometric snapshot, generate a timeliness certificate, and finally use the Beidou atomic clock time, the on-chain time certificate and the timeliness certificate to generate a multi-layer nested timestamp; The signature generation unit is used to generate a visual signature graphic based on the digital watermark and multi-layer nested timestamp, and write the feature vector hash value into the blockchain for evidence storage. The signature graphic is stored in SVG vector format, including a watermark layer, a timestamp ciphertext layer and a visual pattern layer.

[0009] Preferably, in the process of embedding the digital watermark into the intermediate frequency component of the signature image, the adjustment of the embedding strength is based on a feedback control model of network delay environment perception, and the model is expressed as follows: ,in, represents the embedding strength of the mid-frequency component, Indicates the baseline strength, Indicates the real-time network delay, Indicates the preset delay threshold, represents the maximum tolerable delay, Represents the adjustment factor.

[0010] Preferably, the anti-counterfeiting verification module includes: Quantum key distribution unit, used to generate temporary session keys according to the decoyed BB84 protocol, distributed through a 1550nm wavelength single-mode optical fiber channel, equipped with NTRU-743 post-quantum encryption backup channel, and the key life cycle is strongly bound to the verification session; The reverse feature matching unit is used to extract the SM4 encrypted evidence hash value from the blockchain, and after decryption, the bandwidth-constrained derivative dynamic time warping algorithm is used for similarity comparison. The matching threshold is dynamically adjusted according to the risk scenario, and the integrity of the restoration process is proved by zk-STARK; The abnormal behavior analysis unit is used to deploy a bidirectional LSTM network to calculate the risk scores of the three factors of frequency, geography, and equipment in real time. When the trigger level is ≥3, the three-step verification process of biometric re-authentication, remote equipment certification, and manual review is initiated.

[0011] Preferably, the weighted feature fusion algorithm in the information fusion processing module is also implemented by a spatiotemporal convolutional feature fusion network, which includes: Multi-scale temporal convolution layer: dilated causal convolution is used to obtain millisecond-level dynamic changes in biometric data. The convolution kernel dilation rate Increasing exponentially, The formula is: , in, represents the output of the dilated causal convolution, represents the input signal at time t, is the convolution kernel weight, is the bias term, k is the original convolution kernel size; Spherical spatial convolution layer: used to convert geographic location information into three-dimensional spherical coordinates: , in, Indicates longitude, Indicates latitude, Represents three-dimensional spherical coordinates; Generate hierarchical spherical convolution kernels and convolution weights based on HEALPix grid division Constrained by a spherical harmonic basis: , in, is the level, which is used to indicate the resolution of the grid. The higher the level, the finer the grid. Represents the spherical convolution weight, indicating the position on the spherical surface The convolution weight at , represents the coefficients of spherical harmonics, represents spherical harmonics, is the multiplicity, used to represent the orthogonal basis on the sphere, is the preset maximum order; Output spatial feature map ,in The dimension is The spatial feature map in matrix form, represents the set of real numbers; Quantum attention fusion layer: used to map temporal and spatial features to quantum state space: , in, represents the time feature vector, and The quantum state representations of time and space characteristics respectively, as well as Respectively represent the coefficients of time characteristics and space characteristics in the quantum ground state, and represent the projection of the characteristics on the corresponding ground state. and They respectively represent the preset orthogonal ground states, which are used to construct the quantum state space; Entangled states are generated by controlled exchange gates: , in, Represents the generated entangled state, which is used to represent the quantum entanglement of time and space characteristics. and represents the two ground states of the control qubit, Represents the tensor product operation of quantum states, which is used to construct composite quantum systems; performs projection measurements on entangled states and calculates the attention weight matrix : , in, Represents the attention weight matrix The element in the i-th row and j-th column in represents the attention weight between the i-th element of the temporal feature and the j-th element of the spatial feature. represents the observation operator of the element in the i-th row and j-th column, which is used to measure the degree of correlation between the temporal and spatial characteristics in the entangled state. represents the expected value of the observation operator on the entangled state, and represents the correlation strength between the temporal and spatial features at the element in the i-th row and j-th column; Output fused feature vector , represents the operation of expanding a matrix into a vector, Represents the attention weight matrix Kronecker product with temporal and spatial features The matrix multiplication of represents the weighted fusion of features.

[0012] The present invention has achieved at least the following beneficial effects: 1. The present invention breaks through the limitations of the traditional single encryption mode by cross-binding multimodal biometrics and hardware fingerprints, combining quantum keys and blockchain sharding technology.

[0013] 2. The frequency domain modulation technology of dynamic digital watermarking + three-layer timestamp nesting mechanism is used to significantly improve the defense capability against deep fake attacks.

[0014] Other advantages, objectives and features of the present invention will be described in the following description and will be apparent to those skilled in the art to some extent, or those skilled in the art may be taught from the practice of the present invention. The objectives and other advantages of the present invention may be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to make the purpose, technical solution and beneficial effects of the present invention clearer, the present invention provides the following drawings for illustration: Figure 1 It is a structural schematic diagram of an electronic signature generation and anti-counterfeiting system based on multi-source information fusion in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0017] The present invention provides an electronic signature generation and anti-counterfeiting system based on multi-source information fusion, referring to Figure 1 ,include: The multi-source information acquisition module includes a user biometric feature recognition unit, a device fingerprint extraction unit, and a dynamic environment perception unit, which are used to synchronously obtain user fingerprint / iris features, terminal device hardware fingerprints, and timestamps and geographic location information during operation; The information fusion processing module uses a weighted feature fusion algorithm and blockchain encryption anchoring technology to encrypt and compress multi-source information and generate a unique feature vector; The electronic signature generation module generates a visual signature graphic containing a dynamic digital watermark and a multi-layer nested timestamp based on the feature vector, and writes the feature vector hash value into the blockchain for evidence storage; The anti-counterfeiting verification module verifies the authenticity of the signature through the dynamic decryption protocol of quantum key distribution, and supports reverse feature matching verification based on blockchain traceability.

[0018] The working principle and beneficial effects of the above technical solution are as follows: the present invention synchronously obtains the user's biometrics, the terminal device hardware fingerprint, and the timestamp and geographic location information during operation through a multi-source information acquisition module, and uses the weighted feature fusion algorithm and blockchain encryption anchoring technology of the information fusion processing module to encrypt and compress the multi-source information to generate a unique feature vector. The electronic signature generation module creates a visual signature graphic containing a dynamic digital watermark and a multi-layer nested timestamp based on the feature vector, and writes the feature vector hash value into the blockchain for evidence storage. The anti-counterfeiting verification module uses a dynamic decryption protocol of quantum key distribution to verify the authenticity of the signature, and supports reverse feature matching verification based on blockchain traceability. The entire solution improves the security and credibility of the signature, ensures the integrity and non-tamperability of the data, and is easy to operate, adaptable to a variety of scenarios, and has high efficiency and flexibility.

[0019] In a preferred embodiment, the multi-source information acquisition module includes: User biometric identification unit: used to collect fingerprint line features, iris texture phase coding and voiceprint dynamic spectrum through multi-threaded parallelization through fingerprint sensor, iris scanner and microphone array; Device fingerprint extraction unit: used to extract CPU microcode features, baseband chip serial number and GPU rendering fingerprint by parsing the hardware registers of the terminal device, and generate a composite device identification code; Dynamic environment perception unit: used to capture the three-dimensional geographic coordinates, UTC timestamp and device motion trajectory characteristics during operation in real time through the built-in GPS / Beidou dual-mode positioning chip, NTP network timing module and acceleration sensor; The multi-source information collection module runs in isolation through a secure sandbox, and the collected data is transmitted to the information fusion processing module after being signed by HMAC-SHA3.

[0020] The working principle and beneficial effects of the above technical solution are as follows: the multi-source information acquisition module comprehensively acquires user biometrics, device fingerprints and dynamic environment information through a variety of sensors and analysis technologies. In the security sandbox, these data are encrypted and signed and then transmitted to the next module, providing a reliable and rich data source for subsequent information fusion processing, laying the foundation for electronic signature generation and anti-counterfeiting. Multi-dimensional biometric acquisition and device fingerprint extraction, combined with dynamic environment perception, make signature generation based on rich and accurate information, which is difficult to forge. The security sandbox isolation operation and HMAC-SHA3 signature further ensure data security transmission and prevent data leakage and tampering. Multi-threaded parallel acquisition of multiple biometrics improves recognition accuracy, effectively distinguishes different users, and enhances the user identity authentication function of the signature. The dynamic environment perception unit provides time-space related data, so that the signature carries the time-space information during operation, enhances the time-space attributes of the signature, is conducive to subsequent traceability and verification, and meets the time-space authentication requirements in specific scenarios. Multi-threaded parallel acquisition and security sandbox mechanism improve the efficiency of data acquisition and transmission while ensuring data security, reduce operation waiting time, and improve user experience.

[0021] In a preferred embodiment, the information fusion processing module includes: A data preprocessing unit is used to normalize the biometric data, wherein the fingerprint image is denoised using Gabor filtering, and the iris feature is compressed to a 256-dimensional vector through Daubechies wavelet transform; The weighted feature fusion unit dynamically assigns weight coefficients to biological features, equipment features, and environmental features based on the preset environmental risk assessment model, and calculates the fusion features using the weighted Euclidean distance formula: ,in, , , They are the dynamic real-time feature values ​​of biometric features, device features, and environmental features. , , They are the dynamic baseline values ​​of biometrics, device features, and environmental features. , , They are the maximum tolerances of each dimension of biometrics, device features, and environmental features. , , They are the weight coefficients corresponding to the dynamics of biometric features, device features, and environmental features; The blockchain encryption anchor unit is used to encrypt the fused feature value through the national secret SM4 algorithm. After generating a 256-bit feature vector, its hash value is written into the Merkle tree of the Hyperledger Fabric alliance chain, and a timestamp and participating node digital certificate are generated for each signed transaction.

[0022] The working principle and beneficial effects of the above technical solution are as follows: the information fusion processing module normalizes the biometric data through the data preprocessing unit, removes noise and redundant information, and improves data quality. The weighted feature fusion unit dynamically allocates weight coefficients according to the environmental risk assessment model, highlights important features, and improves the pertinence and effectiveness of feature fusion. The blockchain encryption anchor unit uses the national secret SM4 algorithm to encrypt the fused feature value to ensure the confidentiality and integrity of the data. The generated 256-bit feature vector and its hash value are written into the Merkle tree of the alliance chain, and the distributed storage and tamper-proof characteristics of the blockchain are used to realize the credible storage of the feature vector. Each signed transaction generates a timestamp and a digital certificate of the participating nodes to ensure that the time sequence of the signed transaction and the identity of the participating nodes are traceable, thereby enhancing the security and credibility of the system.

[0023] In a preferred embodiment, the electronic signature generation module includes: The watermark embedding unit is used to generate a pseudo-random sequence from the feature vector through chaotic mapping, and to embed the digital watermark in the intermediate frequency component of the signature image using discrete cosine transform. The embedding strength is adaptively adjusted based on the network delay. The timestamp generation unit is used to call the National Time Service Center API to obtain the Beidou atomic clock time, trigger the Ethereum smart contract to generate an on-chain time certificate containing the hash of the previous block, perform SHA-256 hash operation on the signature file content, encrypt it after splicing it with the user's biometric snapshot, generate a timeliness certificate, and finally use the Beidou atomic clock time, the on-chain time certificate and the timeliness certificate to generate a multi-layer nested timestamp; The signature generation unit is used to generate a visual signature graphic based on the digital watermark and multi-layer nested timestamp, and write the feature vector hash value into the blockchain for evidence storage. The signature graphic is stored in SVG vector format, including a watermark layer, a timestamp ciphertext layer and a visual pattern layer.

[0024] The working principle and beneficial effects of the above technical solution are as follows: the electronic signature generation module realizes the secure generation and storage of electronic signatures through the collaborative work of the watermark embedding unit, the timestamp generation unit and the signature generation unit. The watermark embedding unit uses chaotic mapping and discrete cosine transform to embed digital watermarks in the signature image, and the embedding strength is adaptively adjusted according to the network delay, which not only ensures the robustness of the watermark, but also improves the visual quality of the signature image. The timestamp generation unit integrates the Beidou atomic clock time, the on-chain time certificate generated by the Ethereum smart contract, and the SHA-256 hash operation result of the signature file content to generate a multi-layer nested timestamp, which ensures the time sequence and content integrity of the signature file and enhances the credibility and anti-tampering ability of the signature. The signature generation unit combines the digital watermark and the multi-layer nested timestamp to generate a visual signature graphic, and stores it in SVG vector format, which not only contains the watermark layer and the timestamp ciphertext layer, but also contains a visual pattern layer, so that the signature is both visually recognizable and contains rich anti-counterfeiting information. At the same time, the feature vector hash value is written into the blockchain for evidence storage, and the immutable nature of the blockchain is used to further ensure the security and traceability of the signature. This technical solution integrates key information such as feature vectors and timestamps into the signature image through the multi-unit collaboration of the electronic signature generation module to generate an electronic signature with high security and credibility. This technical solution improves the security of the signature, enhances the credibility of the signature, ensures the integrity and traceability of the signature document, and improves the visual quality and anti-counterfeiting ability of the signature image.

[0025] In a preferred embodiment, during the process of embedding the digital watermark into the intermediate frequency component of the signature image, the adjustment of the embedding strength is based on a feedback control model of network delay environment perception, and the model is expressed as follows: ,in, represents the embedding strength of the mid-frequency component, Indicates the baseline strength, Indicates the real-time network delay, Indicates the preset delay threshold, represents the maximum tolerable delay, Represents the adjustment factor.

[0026] In a preferred embodiment, the anti-counterfeiting verification module includes: Quantum key distribution unit, used to generate temporary session keys according to the decoyed BB84 protocol, distributed through a 1550nm wavelength single-mode optical fiber channel, equipped with NTRU-743 post-quantum encryption backup channel, and the key life cycle is strongly bound to the verification session; The reverse feature matching unit is used to extract the SM4 encrypted evidence hash value from the blockchain, and after decryption, the bandwidth-constrained derivative dynamic time warping algorithm is used for similarity comparison. The matching threshold is dynamically adjusted according to the risk scenario, and the integrity of the restoration process is proved by zk-STARK; The abnormal behavior analysis unit is used to deploy a bidirectional LSTM network to calculate the risk scores of the three factors of frequency, geography, and equipment in real time. When the trigger level is ≥3, the three-step verification process of biometric re-authentication, remote equipment certification, and manual review is initiated.

[0027] The working principle and beneficial effects of the above technical solution are as follows: the anti-counterfeiting verification module realizes the security verification and risk prevention and control of electronic signatures through the collaborative work of the quantum key distribution unit, the reverse feature matching unit and the abnormal behavior analysis unit. The quantum key distribution unit uses the entrapped BB84 protocol to generate temporary session keys and distributes them through a 1550nm wavelength single-mode optical fiber channel. It is also equipped with a NTRU-743 post-quantum encryption backup channel to ensure the security and reliability of key distribution. The key life cycle is strongly bound to the verification session, further enhancing the security of key management. The reverse feature matching unit extracts the SM4 encrypted evidence hash value from the blockchain, and after decryption, the bandwidth-constrained derivative dynamic time warping algorithm is used for similarity comparison. The matching threshold is dynamically adjusted according to the risk scenario to ensure the accuracy and adaptability of feature matching. The integrity of the restoration process is proved by zk-STARK, which ensures the transparency and credibility of the verification process. The abnormal behavior analysis unit deploys a bidirectional LSTM network to calculate the risk scores of the three factors of frequency, geography, and equipment in real time. When the trigger level is ≥3, it starts the three-step verification process of biometric re-authentication, remote equipment certification, and manual review, effectively preventing abnormal behavior and potential risks, and improving the security and reliability of the system. This technical solution realizes the security verification and risk prevention and control of electronic signatures through the multi-unit collaboration of anti-counterfeiting verification modules, using quantum key distribution, blockchain technology, dynamic time warping algorithms, and abnormal behavior analysis. This technical solution improves the security of signature verification, enhances the risk prevention and control capabilities of the system, ensures the transparency and credibility of the verification process, and realizes effective monitoring and timely response to abnormal behavior.

[0028] In a preferred embodiment, the weighted feature fusion algorithm in the information fusion processing module is also implemented by a spatiotemporal convolutional feature fusion network, which includes: Multi-scale temporal convolution layer: dilated causal convolution is used to obtain millisecond-level dynamic changes in biometric data. The convolution kernel dilation rate Increasing exponentially, The formula is: , in, represents the output of the dilated causal convolution, represents the input signal at time t, is the convolution kernel weight, is the bias term, k is the original convolution kernel size; Spherical spatial convolution layer: used to convert geographic location information into three-dimensional spherical coordinates: , in, Indicates longitude, Indicates latitude, Represents three-dimensional spherical coordinates; Generate hierarchical spherical convolution kernels and convolution weights based on HEALPix grid division Constrained by a spherical harmonic basis: , in, is the level, which is used to indicate the resolution of the grid. The higher the level, the finer the grid. Represents the spherical convolution weight, indicating the position on the spherical surface The convolution weight at , represents the coefficients of spherical harmonics, represents spherical harmonics, is the multiplicity, used to represent the orthogonal basis on the sphere, is the preset maximum order; Output spatial feature map ,in The dimension is The spatial feature map in matrix form, represents the set of real numbers; Quantum attention fusion layer: used to map temporal and spatial features to quantum state space: , in, represents the time feature vector, and The quantum state representations of time and space characteristics respectively, as well as Respectively represent the coefficients of time characteristics and space characteristics in the quantum ground state, and represent the projection of the characteristics on the corresponding ground state. and They respectively represent the preset orthogonal ground states, which are used to construct the quantum state space; Entangled states are generated by controlled exchange gates: , in, Represents the generated entangled state, which is used to represent the quantum entanglement of time and space characteristics. and represents the two ground states of the control qubit, Represents the tensor product operation of quantum states, which is used to construct composite quantum systems; performs projection measurements on entangled states and calculates the attention weight matrix : , in, Represents the attention weight matrix The element in the i-th row and j-th column in represents the attention weight between the i-th element of the temporal feature and the j-th element of the spatial feature. represents the observation operator of the element in the i-th row and j-th column, which is used to measure the degree of correlation between the temporal and spatial characteristics in the entangled state. represents the expected value of the observation operator on the entangled state, and represents the correlation strength between the temporal and spatial features at the element in the i-th row and j-th column; Output fused feature vector , represents the operation of expanding a matrix into a vector, Represents the attention weight matrix Kronecker product with temporal and spatial features The matrix multiplication of represents the weighted fusion of features.

[0029] The beneficial effect of the above technical solution is that the spatiotemporal convolution feature fusion network includes a multi-scale time convolution layer, a spatial feature extraction layer and a spatiotemporal feature fusion layer. The multi-scale time convolution layer uses dilated causal convolution to obtain the millisecond-level dynamic changes of biometric data. The convolution kernel dilation rate increases exponentially, which can capture the dynamic changes of biometric data at different time scales. The spatial feature extraction layer extracts spatial features from device fingerprints and geographic location information, extracts local spatial features using convolution operations, and reduces feature dimensions through pooling operations. The spatiotemporal feature fusion layer fuses the temporal features output by the multi-scale time convolution layer with the spatial features output by the spatial feature extraction layer, and uses a weighted feature fusion algorithm to assign different weights to different features to generate a comprehensive feature vector. The entire technical solution uses a spatiotemporal convolution feature fusion network to deeply process and fuse multi-source information, thereby improving data quality and feature expression capabilities. This technical solution improves data quality, enhances feature expression capabilities, improves system security and credibility, and achieves efficient data fusion and processing.

[0030] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and details without departing from the scope defined by the claims of the present invention.

Claims

1. An electronic signature generation and anti-counterfeiting system based on multi-source information fusion, characterized in that: include: The multi-source information acquisition module includes a user biometric feature recognition unit, a device fingerprint extraction unit, and a dynamic environment perception unit, which are used to synchronously obtain user fingerprint / iris features, terminal device hardware fingerprints, and timestamps and geographic location information during operation; The information fusion processing module uses a weighted feature fusion algorithm and blockchain encryption anchoring technology to encrypt and compress multi-source information and generate a unique feature vector; The electronic signature generation module generates a visual signature graphic containing a dynamic digital watermark and a multi-layer nested timestamp based on the feature vector, and writes the feature vector hash value into the blockchain for evidence storage; The anti-counterfeiting verification module verifies the authenticity of the signature through the dynamic decryption protocol of quantum key distribution, and supports reverse feature matching verification based on blockchain traceability.

2. According to claim 1, the electronic signature generation and anti-counterfeiting system based on multi-source information fusion is characterized in that: The multi-source information acquisition module includes: User biometric identification unit: used to collect fingerprint line features, iris texture phase coding and voiceprint dynamic spectrum through multi-threaded parallelization through fingerprint sensor, iris scanner and microphone array; Device fingerprint extraction unit: used to extract CPU microcode features, baseband chip serial number and GPU rendering fingerprint by parsing the hardware registers of the terminal device, and generate a composite device identification code; Dynamic environment perception unit: used to capture the three-dimensional geographic coordinates, UTC timestamp and device motion trajectory characteristics during operation in real time through the built-in GPS / Beidou dual-mode positioning chip, NTP network timing module and acceleration sensor; The multi-source information collection module runs in isolation through a secure sandbox, and the collected data is transmitted to the information fusion processing module after being signed by HMAC-SHA3.

3. The electronic signature generation and anti-counterfeiting system based on multi-source information fusion according to claim 1 is characterized in that: The information fusion processing module includes: A data preprocessing unit is used to normalize the biometric data, wherein the fingerprint image is denoised using Gabor filtering, and the iris feature is compressed to a 256-dimensional vector through Daubechies wavelet transform; The weighted feature fusion unit dynamically assigns weight coefficients to biological features, equipment features, and environmental features based on the preset environmental risk assessment model, and calculates the fusion features using the weighted Euclidean distance formula: ,in, , , They are the dynamic real-time feature values ​​of biometric features, device features, and environmental features. , , They are the dynamic baseline values ​​of biometrics, device features, and environmental features. , , They are the maximum tolerances of each dimension of biometrics, device features, and environmental features. , , They are the weight coefficients corresponding to the dynamics of biometric features, device features, and environmental features; The blockchain encryption anchor unit is used to encrypt the fused feature value through the national secret SM4 algorithm. After generating a 256-bit feature vector, its hash value is written into the Merkle tree of the Hyperledger Fabric alliance chain, and a timestamp and participating node digital certificate are generated for each signed transaction.

4. The electronic signature generation and anti-counterfeiting system based on multi-source information fusion according to claim 1 is characterized in that: The electronic signature generation module includes: The watermark embedding unit is used to generate a pseudo-random sequence from the feature vector through chaotic mapping, and to embed the digital watermark in the intermediate frequency component of the signature image using discrete cosine transform. The embedding strength is adaptively adjusted based on the network delay. The timestamp generation unit is used to call the National Time Service Center API to obtain the Beidou atomic clock time, trigger the Ethereum smart contract to generate an on-chain time certificate containing the hash of the previous block, perform SHA-256 hash operation on the signature file content, encrypt it after splicing it with the user's biometric snapshot, generate a timeliness certificate, and finally use the Beidou atomic clock time, the on-chain time certificate and the timeliness certificate to generate a multi-layer nested timestamp; The signature generation unit is used to generate a visual signature graphic based on the digital watermark and multi-layer nested timestamp, and write the feature vector hash value into the blockchain for evidence storage. The signature graphic is stored in SVG vector format, including a watermark layer, a timestamp ciphertext layer and a visual pattern layer.

5. The electronic signature generation and anti-counterfeiting system based on multi-source information fusion according to claim 4 is characterized in that: In the process of embedding the digital watermark into the intermediate frequency component of the signature image, the adjustment of the embedding strength is based on the feedback control model of network delay environment perception, which is expressed as follows: ,in, represents the embedding strength of the mid-frequency component, Indicates the baseline strength, Indicates the real-time network delay, Indicates the preset delay threshold, represents the maximum tolerable delay, Represents the adjustment factor.

6. The electronic signature generation and anti-counterfeiting system based on multi-source information fusion according to claim 1 is characterized in that: The anti-counterfeiting verification module includes: Quantum key distribution unit, used to generate temporary session keys according to the decoyed BB84 protocol, distributed through a 1550nm wavelength single-mode optical fiber channel, equipped with NTRU-743 post-quantum encryption backup channel, and the key life cycle is strongly bound to the verification session; The reverse feature matching unit is used to extract the SM4 encrypted evidence hash value from the blockchain, and after decryption, the bandwidth-constrained derivative dynamic time warping algorithm is used for similarity comparison. The matching threshold is dynamically adjusted according to the risk scenario, and the integrity of the restoration process is proved by zk-STARK; The abnormal behavior analysis unit is used to deploy a bidirectional LSTM network to calculate the risk scores of the three factors of frequency, geography, and equipment in real time. When the trigger level is ≥3, the three-step verification process of biometric re-authentication, remote equipment certification, and manual review is initiated.

7. The electronic signature generation and anti-counterfeiting system based on multi-source information fusion according to claim 1 is characterized in that: The weighted feature fusion algorithm in the information fusion processing module is also implemented through a spatiotemporal convolutional feature fusion network, which includes: Multi-scale temporal convolution layer: dilated causal convolution is used to obtain millisecond-level dynamic changes in biometric data. The convolution kernel dilation rate Increasing exponentially, The formula is: , in, represents the output of the dilated causal convolution, represents the input signal at time t, is the convolution kernel weight, is the bias term, k is the original convolution kernel size; Spherical spatial convolution layer: used to convert geographic location information into three-dimensional spherical coordinates: , in, Indicates longitude, Indicates latitude, Represents three-dimensional spherical coordinates; Generate hierarchical spherical convolution kernels and convolution weights based on HEALPix grid division Constrained by a spherical harmonic basis: , in, is the level, which is used to indicate the resolution of the grid. The higher the level, the finer the grid. Represents the spherical convolution weight, indicating the position on the spherical surface The convolution weight at , represents the coefficients of spherical harmonics, represents spherical harmonics, is the multiplicity, used to represent the orthogonal basis on the sphere, is the preset maximum order; Output spatial feature map ,in The dimension is The spatial feature map in matrix form, represents the set of real numbers; Quantum attention fusion layer: used to map temporal and spatial features to quantum state space: , in, represents the time feature vector, and The quantum state representations of time and space characteristics respectively, as well as Respectively represent the coefficients of time characteristics and space characteristics in the quantum ground state, and represent the projection of the characteristics on the corresponding ground state. and They respectively represent the preset orthogonal ground states, which are used to construct the quantum state space; Entangled states are generated by controlled exchange gates: , in, Represents the generated entangled state, which is used to represent the quantum entanglement of time and space characteristics. and represents the two ground states of the control qubit, Represents the tensor product operation of quantum states, which is used to construct composite quantum systems; performs projection measurements on entangled states and calculates the attention weight matrix : ， in, Represents the attention weight matrix The element in the i-th row and j-th column in represents the attention weight between the i-th element of the temporal feature and the j-th element of the spatial feature. represents the observation operator of the element in the i-th row and j-th column, which is used to measure the degree of correlation between the temporal and spatial characteristics in the entangled state. represents the expected value of the observation operator on the entangled state, and represents the correlation strength between the temporal and spatial features at the element in the i-th row and j-th column; Output fused feature vector , represents the operation of expanding a matrix into a vector, Represents the attention weight matrix Kronecker product with temporal and spatial features The matrix multiplication of represents the weighted fusion of features.

Images